chipi/agentic-ai-homelab/host-run

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Run a multi-line, quoted or JSON-bearing command on a homelab host (the Mac mini, the DGX, the prod VPS) from a script file instead of inline over ssh — it copies the file, runs it with bash or python3, streams the output, returns the remote exit code and deletes the copy. Use whenever a remote command has more than one line, quotes inside quotes, JSON, a heredoc or inline Python, before writing `ssh host '...'` by hand.

Install

npx vskill@latest install chipi/agentic-ai-homelab/host-run

SKILL.md

host-run

Inline commands over ssh break in ways that look like real failures:

  • zsh on the laptop expands =word (echo ===== → zsh: ==== not found);
  • nested quotes corrupt JSON bodies silently (Invalid JSON);
  • inline Python f-strings can't contain backslashes;
  • non-interactive shells on the mini lack /usr/local/bin, so docker isn't found.

All of these hit this repo's sessions repeatedly (2026-10-16/17). A script file has none of them.

Run

bash
# write the commands to a file in your scratchpad, then:
~/.claude/skills/host-run/scripts/run.sh <host> <file.sh|file.py> [args...]
HostReaches
homelab (or mini)the Mac mini, operator account (ssh -i ~/.ssh/homelab_mini -o IdentitiesOnly=yes markodragoljevic@homelab)
homelab-claudethe mini's claude account (ssh homelab-claude)
dgxdgx-llm-1
proddeploy@prod-podcast
  • .py files run with python3, anything else with bash.
  • /usr/local/bin and /opt/homebrew/bin are put on PATH, so docker works on the mini.
  • Arguments are passed literally (each one %q-quoted).
  • The exit status is the remote script's: 2 means bad usage, 3 means the host is unreachable.
  • The remote copy lives in /tmp/host-run.XXXXXX (mode 700) and is removed on exit.

Rules

  • Secrets never go in the file or the arguments. The script loads them on the host

(set -a; . ~/…/.env; set +a), the way the handbook's recipes do.

  • Read-only by default. A script that writes (deletes, restarts, mints) needs the same approval

as running those commands by hand.

  • Keep the file in your scratchpad, not in a repo.

Verified

2026-10-17 on homelab and dgx:

  • arguments "arg one" '$HOME' '=x' arrived literally;
  • JSON with spaces round-tripped;
  • echo ===== printed;
  • an f-string with a backslash ran;
  • docker resolved;
  • exit 7 came back as 7, and an unknown host exited 2;
  • no /tmp/host-run.* files were left on either host.

Not covered

  • Interactive commands (sudo with a password, TUI tools).
  • Copying files back; use scp for that.
  • Long-running jobs; the script runs in the foreground of the ssh session.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/chipi/agentic-ai-homelab/host-run/badge)](https://verified-skill.com/skills/chipi/agentic-ai-homelab/host-run)

Something wrong with this skill or its page? Tell us.